VST 3B needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.4 GB (Q2_K) to 6.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
VST 3B – a 3.4B parameter video‑LLM with vision and tool use
VST 3B is a 3.4B parameter model built on the qwen2vl architecture. It supports vision and tool use and was trained on 128000 context tokens. The model is released under the apache-2.0 license.
Good at
- Vision and tool integration
- Streaming video understanding
- Real‑time reasoning
Limits
- No vision support on older hardware
- Requires at least 2.2 GB VRAM for Q2_K
- License is apache-2.0
Best for
- Video analysis pipelines
- Interactive video assistants
- Tool‑augmented video tasks
Who it’s for. Developers building video‑centric LLM applications who need a lightweight yet capable model. The model is suitable for research and production environments that can accommodate its VRAM requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 2.6 GB | Fits | Get file → | |
| IQ4_XS | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_S | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q5_K_S | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 3.6 GB | 4.4 GB | Fits | Get file → | |
| F16 | 6.8 GB | 7.6 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.1 GB, estimated 2.9 GB memory). If 12 GB VRAM is available, Q5_K_M (2.44 GB, 3.2 GB memory) offers better quality. For maximum fidelity, F16 (6.8 GB, 7.6 GB memory) is recommended if memory permits.
What GPU do you need for VST 3B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q6_K (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.4 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.8 GB file, about 7.6 GB in use).
Which VST 3B quant should you choose?
Q4_K_M is the usual starting point for VST 3B: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 1.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about VST 3B
How much VRAM does VST 3B need?
About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run VST 3B on an 8 GB GPU?
Yes, with F16: the 6.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VST 3B GGUF?
It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.6 GB, Q3_K_M is 1.7 GB, Q3_K_L is 1.8 GB, IQ4_XS is 1.9 GB, Q4_K_S is 2.0 GB and 6 more.
What context length does VST 3B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download VST 3B GGUF?
The files are on Hugging Face in the mradermacher/VST-3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does VST 3B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run VST 3B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.9 GB memory at 8k context, fitting within 8 GB VRAM.
Does VST 3B support vision tasks?
Yes, the model has detected vision ability and can process video input.